CN113099870B - Self-adaptive flower thinning machine and flower thinning method - Google Patents

Abstract

The invention discloses a self-adaptive flower thinning machine and a flower thinning method, wherein the self-adaptive flower thinning machine comprises an operation carrier, a multi-section self-adaptive flower thinning device, an intelligent flower density identification system, a self-adaptive control system and a hydraulic drive station, wherein the multi-section self-adaptive flower thinning device, the intelligent flower density identification system, the self-adaptive control system and the hydraulic drive station are arranged on the operation carrier; the multi-section self-adaptive flower thinning device comprises a base mechanism, a profiling mechanism, a mark thinning mechanism and a flower thinning mechanism, wherein the mark thinning mechanism is arranged on the base mechanism, the profiling mechanism and the flower thinning mechanism are multiple, the multiple profiling mechanisms and the multiple flower thinning mechanisms correspond to each other one by one, each flower thinning mechanism is arranged on the corresponding profiling mechanism, and the multiple profiling mechanisms are sequentially arranged on the mark thinning mechanism from top to bottom. The invention can improve the identification precision and the self-adaptive flower thinning capability of the fruit tree flowers, reduce the labor intensity and improve the flower thinning efficiency and proportion.

Description

Self-adaptive flower thinning machine and flower thinning method

Technical Field

The invention relates to a self-adaptive flower thinning machine and a flower thinning method, and belongs to the field of agricultural mechanized, automatic and intelligent production.

Background

Flower thinning is an important measure for improving the fruit quality, reducing nutrient consumption and continuously stabilizing high yield, and is also one of the more heavy links of orchard production operation. The mechanical flower thinning is to separate flower stalks, flower bunches and fruit trees by a physical method to achieve the purpose of flower thinning, can be used for thinning flowers and young fruits, concentrates effective flower thinning treatment, and can avoid the phenomenon of fruit bearing of the fruit trees in big and small years; compared with manual flower thinning and chemical flower thinning, the mechanical flower thinning operation has the highest efficiency, and the problems of pesticide residue, environmental pollution and the like do not exist; furthermore, mechanical thinning is not affected by climatic conditions. Mechanical flower thinning is a new technology for improving efficiency and reducing cost in large-scale orchard cultivation, and has important significance for realizing whole-process mechanization of orchard production. The research on mechanical flower thinning of fruit trees is late in China, and the adaptability of foreign machinery in China is limited by the differences of fruit tree cultivation modes and agricultural techniques at home and abroad.

Therefore, in the last two decades, relevant personnel of scientific research institutions such as Chinese agriculture university, northwest agriculture and forestry science and technology university, south China agriculture university, Qingdao agriculture university, Jiangsu province agriculture academy and the like begin to conduct mechanical flower thinning research on fruit trees; the intelligent flower thinning machine is different from a foreign road which is firstly mechanized and then intelligentized, is the synchronous development of mechanical structure diversification and control system intelligentization, and realizes the degree of the flower thinning machine from no machine to certain automatic operation; for example, a suspension type litchi fruit tree electric flexible flower thinning machine based on ultrasonic detection profiling developed by southern China agricultural university, a short dense apple tree main shaft type flower thinning machine developed by Qingdao agricultural university, a three-arm machine-mounted canopy frame Y-shaped pear garden flower thinning machine developed by Jiangsu province agricultural academy, and the like. However, the flower thinning machine with high automation degree, complex structure type and strong mark tracking and profiling effect adaptability has no relevant reports of being put into use or being produced in a production mode. Therefore, there is a need to further improve the flower thinning machine and the intelligent operation level of the flower thinning machine.

Disclosure of Invention

The invention aims to provide a self-adaptive flower thinning machine which can effectively solve the problems of intelligent flower and fruit identification and self-adaptive flower thinning in an orchard in the prior art, improve the identification precision and self-adaptive flower thinning capability of fruit trees and flowers, reduce the labor intensity and improve the flower thinning efficiency and proportion.

Another objective of the present invention is to provide a flower thinning method implemented based on the above adaptive flower thinning machine.

The purpose of the invention can be achieved by adopting the following technical scheme:

a self-adaptive flower thinning machine comprises an operation carrier, a multi-section self-adaptive flower thinning device, an intelligent flower density identification system, a self-adaptive control system and a hydraulic drive station, wherein the multi-section self-adaptive flower thinning device, the intelligent flower density identification system, the self-adaptive control system and the hydraulic drive station are arranged on the operation carrier;

the multi-section self-adaptive flower thinning device comprises a base mechanism, a plurality of profiling mechanisms, a label patrolling mechanism and a flower thinning mechanism, wherein the label patrolling mechanism is arranged on the base mechanism, the profiling mechanisms and the flower thinning mechanism are multiple, the profiling mechanisms and the flower thinning mechanisms are in one-to-one correspondence, each flower thinning mechanism is arranged on the corresponding profiling mechanism, the profiling mechanisms are sequentially arranged on the label patrolling mechanism from top to bottom, the profiling mechanisms can move relative to the label patrolling mechanism, and the label patrolling mechanism can move relative to the base mechanism to complete target searching and positioning;

the self-adaptive control system is respectively connected with the profiling mechanism, the mark patrol mechanism, the hydraulic drive station and the intelligent flower density recognition system, and the hydraulic drive station is respectively connected with the flower thinning mechanism, the mark patrol mechanism and the operation carrier.

Furthermore, the intelligent flower density recognition system comprises a camera and a processor, the camera is connected with the processor, the camera is in a horizontal visual angle, the visual field of the camera comprises the whole flower thinning working range, and the processor is connected with the self-adaptive control system;

the camera is used for shooting the fruit tree flower image;

the processor is used for acquiring a plurality of fruit tree flower images; denoising and standardizing each fruit tree flower image; extracting a fruit tree flower and leaf feature map in the processed fruit tree flower and leaf image by using a trained deep convolutional neural network; generating a fruit tree flower and leaf prediction graph according to the fruit tree flower and leaf characteristic graph so as to obtain a fruit tree flower and leaf segmentation graph; counting the number of pixels belonging to flowers and the number of pixels belonging to leaves according to the fruit tree flower and leaf segmentation map; calculating the density of the flower according to the number of the pixels of the flower and the number of the pixels of the leaves; the density of flowers in each image of the fruit tree flower is converted to an analog quantity.

Further, adaptive control system includes host computer, programmable logic controller, analog-to-digital conversion module, digital-to-analog conversion module, communication module and relay group, programmable logic controller is connected with profiling mechanism, mark mechanism, analog-to-digital conversion module, digital-to-analog conversion module, communication module, relay group respectively, communication module and host computer are connected, analog-to-digital conversion module and intelligent flower density identification system are connected, digital-to-analog conversion module and relay group are connected with the hydraulic drive station.

Furthermore, the hydraulic drive station comprises a power source and a hydraulic control element, the hydraulic control element is respectively connected with the flower thinning mechanism, the label inspection mechanism and the power source, and the power source is connected with the operation carrier.

Further, every profiling mechanism includes crossbeam, first floor, second floor, electric putter and support, the crossbeam is installed on patrolling mark mechanism, first floor and second floor all have two, and two first floors are fixed on the position between the crossbeam both ends, and set up the both sides at the crossbeam relatively, are provided with a plurality of regulation holes on every first floor, and two second floors are articulated with the support, and two second floors are fixed at the front end of crossbeam, and set up the both sides at the crossbeam relatively, electric putter and adaptive control system are connected, and electric putter's flexible end is articulated with the support, and electric putter's stiff end passes through the regulation hole and articulates with two first floors, and electric putter can drive the support and rotate around the pin joint of second floor and support, the support is used for installing the flower thinning mechanism that corresponds.

Further, the support includes first fixed plate, second fixed plate, riser and curb plate, the curb plate is two, and two curb plate relatively fixed are on the riser, first fixed plate and second fixed plate are fixed from top to bottom on the riser to with two curb plate fixed connection, first fixed plate is used for the fixed flower axle of dredging that corresponds the flower mechanism of dredging, the second fixed plate is used for the fixed hydraulic motor that corresponds the flower mechanism of dredging.

Further, every flower thinning mechanism includes hydraulic motor, shaft coupling, flower thinning shaft and flower thinning adhesive tape, flower thinning adhesive tape has a plurality ofly, and a plurality ofly flower thinning adhesive tape sets up at flower thinning epaxial, flower thinning shaft passes through the shaft coupling and is connected with hydraulic motor, hydraulic motor and flower thinning shaft are installed on the profiling mechanism who corresponds, and hydraulic motor is connected with the hydraulic drive station.

Furthermore, hydraulic cylinder, stay-supported displacement sensor, sensor support and L type support, hydraulic cylinder sets up on base mechanism, and hydraulic cylinder is connected with the hydraulic drive station, the sensor support sets up on hydraulic cylinder, stay-supported displacement sensor sets up on L type support, and stay-supported displacement sensor passes through the stay wire and is connected with the sensor support, and stay-supported displacement sensor is connected with self-adaptation control system.

Further, base mechanism includes base support, mounting bracket, first supporting component, second supporting component, first pillar, second pillar and third pillar are fixed on base support from the front to the back in proper order, first supporting component sets up on first pillar, second supporting component sets up on the second pillar, first supporting component and second supporting component are used for supporting and patrolling mark mechanism, the mounting bracket is fixed on the third pillar, and the mounting bracket is used for installing and patrols the hydraulic cylinder of mark mechanism.

The other purpose of the invention can be achieved by adopting the following technical scheme:

a flower thinning method implemented based on the adaptive flower thinning machine, the method comprising:

before thinning flowers of fruit trees in the same row, pre-adjusting the extending distance of a cross beam of the profiling mechanism according to the age of the fruit trees and the shape of the fruit trees, and ensuring the operation range of the patrol mechanism and the profiling work of the canopy of the fruit trees;

after the intelligent flower density recognition system reaches the position to be thinned, the intelligent flower density recognition system carries out intelligent recognition to obtain information of the position and the density of the fruit tree flowers, and the information is transmitted to the self-adaptive control system;

after receiving the information transmitted by the intelligent flower density recognition system, the self-adaptive control system judges the patrol displacement, the profiling angle and the rotational speed of the flower thinning shaft, and converts the patrol displacement, the profiling angle and the rotational speed of the flower thinning shaft into a control quantity of a hydraulic drive station and a control quantity of an electric push rod of a profiling mechanism;

after the relative position of the fruit tree to be thinned is reached, the patrol mechanism acts after the adaptive control system sends an instruction, so that the thinning mechanism moves horizontally to finish patrol, and the distance between the patrol mechanism and the fruit tree to be thinned is ensured to be within a constant range;

according to the branch part to be thinned of the fruit tree to be thinned, a plurality of profiling mechanisms work simultaneously, and the action of an electric push rod of the profiling mechanism is controlled, so that the precision profiling is ensured;

after profiling, the hydraulic motor of the flower thinning mechanism is controlled to act to drive the flower thinning shaft and the flower thinning adhesive tape of the flower thinning mechanism to rotate, and self-adaptive flower thinning operation is carried out on branches to be thinned of fruit trees to be thinned.

Compared with the prior art, the invention has the following beneficial effects:

1. the intelligent flower density recognition system is used for intelligently recognizing to obtain the position and the density information of the fruit tree flowers, the information is transmitted to the self-adaptive control system, and the self-adaptive control system judges the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft after receiving the information transmitted by the intelligent flower density recognition system, converts the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft into the control quantity of the hydraulic drive station and the control quantity of the electric push rod of the profiling mechanism, further completes the self-adaptive flower thinning operation, can improve the fruit tree flower recognition precision and the self-adaptive flower thinning capability, reduces the labor intensity and improves the flower thinning efficiency and proportion.

2. The intelligent flower density recognition system extracts the characteristic diagram of the flower and leaf of the fruit tree through the trained deep convolution neural network, can accurately segment the flower area of the fruit tree in real time, calculates the flower density, converts the flower density into an analog quantity, transmits the analog quantity signal to the self-adaptive control system, and provides visual support for automatic flower thinning; and a plurality of stability-maintaining components can be arranged, so that the whole intelligent flower density identification system can work more stably.

2. The multi-section self-adaptive flower thinning device is provided with the plurality of profiling mechanisms and the plurality of flower thinning mechanisms, the plurality of profiling mechanisms are sequentially arranged on the label inspection mechanism from top to bottom, the plurality of profiling mechanisms can move relative to the label inspection mechanism, the multi-section self-adaptive flower thinning device can be guaranteed to adapt to the fruit tree canopies with different tree ages, the pre-adjusting profiling effect is achieved, each profiling mechanism adjusts profiling in the flower thinning process of the same fruit tree, the multi-section self-adaptive flower thinning device meets the profiling requirements of the fruit tree canopies with the same tree age, and each flower thinning mechanism is arranged on the corresponding profiling mechanism, so that the multi-section self-adaptive flower thinning operation can be achieved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.

Fig. 1 is a perspective structural view of an adaptive flower thinning machine according to an embodiment of the present invention.

Fig. 2 is a front structural view of the adaptive flower thinning machine according to the embodiment of the present invention.

Fig. 3 is a side structure diagram of the adaptive flower thinning machine according to the embodiment of the present invention.

Fig. 4 is a plan view of the multi-section adaptive flower thinning apparatus according to the embodiment of the invention.

Fig. 5 is an enlarged view of a portion a in fig. 4.

Fig. 6 is an enlarged view at B in fig. 4.

Fig. 7 is a perspective structural view of a copying mechanism in the multi-section adaptive flower thinning apparatus according to the embodiment of the invention.

Fig. 8 is a perspective view of a flower thinning mechanism in the multi-section adaptive flower thinning apparatus according to the embodiment of the invention.

Fig. 9 is a perspective view of a base mechanism in the multi-section adaptive flower thinning apparatus according to the embodiment of the invention.

Fig. 10 is a flowchart of feature extraction performed by the intelligent flower density recognition system according to the embodiment of the present invention.

Fig. 11 is a schematic diagram of a hydraulic drive station of an embodiment of the present invention.

FIG. 12 is a functional block diagram of an adaptive control system according to an embodiment of the present invention.

Wherein, 1-a base mechanism, 101-a base support, 102-a mounting rack, 103-a first support, 104-a second support, 105-a third support, 106-a first support shaft, 107-a second support shaft, 108-a first bearing fixing sleeve, 109-a second bearing fixing sleeve, 2-a profiling mechanism, 201-a crossbeam, 202-a first ribbed plate, 2021-an adjusting hole, 203-a second ribbed plate, 204-an electric push rod, 205-a first pin shaft, 206-a second pin shaft, 207-a third pin shaft, 208-a first bearing, 209-a first fixing plate, 210-a second fixing plate, 211-a vertical plate, 212-a side plate, 213-a second bearing, 3-a label inspection mechanism, 301-a hydraulic oil cylinder and 302-a stay wire type displacement sensor, 303-a sensor support, 304-an L-shaped support, 305-a sensor fixing frame, 4-a flower thinning mechanism, 401-a hydraulic motor, 4011-a hydraulic oil port, 402-a coupler, 403-a flower thinning shaft, 4031-a threaded hole, 4032-a through hole, 404-a flower thinning adhesive tape, 5-a crawler chassis, 6-a camera, 7-a control cabinet, 8-a power source, 9-a hydraulic control element and 10-an adjustable supporting rod.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and all other embodiments obtained by a person of ordinary skill in the art without making creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.

Example (b):

as shown in fig. 1 to fig. 3, the present embodiment provides an adaptive flower thinning machine, which includes an operation carrier, a multi-stage adaptive flower thinning apparatus, an intelligent flower density identification system, an adaptive control system, and a hydraulic drive station, wherein the multi-stage adaptive flower thinning apparatus, the intelligent flower density identification system, the adaptive control system, and the hydraulic drive station are disposed on the operation carrier, the multi-stage adaptive flower thinning apparatus includes a base mechanism 1, a profiling mechanism 2, a label tracking mechanism 3, and a flower thinning mechanism 4, the label tracking mechanism 3 is disposed on the base mechanism 1, the profiling mechanisms 2 and the flower thinning mechanisms 4 are all three, the three profiling mechanisms 2 and the three flower thinning mechanisms 4 are in one-to-one correspondence, each flower thinning mechanism 4 is disposed on the corresponding profiling mechanism 2, the three profiling mechanisms 2 are sequentially disposed on the label tracking mechanism 3 from top to bottom, and the plurality of profiling mechanisms 2 can move relative to the label tracking mechanism 3, the label inspection mechanism 3 can move relative to the base mechanism 1 to complete target searching and positioning; the operation carrier is a crawler chassis 5 and can carry a multi-section type self-adaptive flower thinning device, an intelligent flower density identification system, a self-adaptive control system and a hydraulic drive station; the intelligent flower density recognition system comprises a camera 6 and a processor (not shown in the figure); the main components of the adaptive control system are mounted in a control cabinet 7; the hydraulic drive station comprises a power source 8 and a hydraulic control element 9.

As shown in fig. 4-5 and 7, each profiling mechanism 2 comprises a beam 201, a first rib plate 202, a second rib plate 203, an electric push rod 204 and a bracket, wherein the beam 201 is mounted on the patrol marking mechanism 3 and can move relative to the patrol marking mechanism 3, so that the adaptability to fruit tree canopies with different tree ages can be ensured, and a pre-adjustment profiling effect can be achieved; the two first rib plates 202 and the two second rib plates 203 are both provided, the two first rib plates 202 are fixed between two ends of the cross beam 201 and are oppositely arranged on two sides of the cross beam 201, a plurality of adjusting holes 2021 are drilled on each first rib plate 202, the two second rib plates 203 are fixed at the front end of the cross beam 201 and are oppositely arranged on two sides of the cross beam 201, the first rib plates 202 and the second rib plates 203 can be fixed on the cross beam 201 in a welding mode, the two second rib plates 203 are hinged with a bracket, the electric push rod 204 is connected with an adaptive control system, the electric push rod 204 is provided with a telescopic end and a fixed end, the telescopic end of the electric push rod 204 is hinged with the bracket, the fixed end of the electric push rod 204 is hinged with the two first rib plates 202 through the adjusting holes 2021, the fixed end position of the electric push rod 204 can be adjusted through the adjusting holes 2021, the electric push rod 204 can drive the bracket to rotate around a hinge point of the second rib plates 203 and the bracket, adjusting profiling for the same row of fruit trees in the flower thinning process to meet the profiling requirements of crown layers of different fruit trees of the same age; the bracket is used for installing the corresponding flower thinning mechanism 4.

In order to realize that the two second rib plates 203 are hinged to the bracket, the telescopic end of the electric push rod 204 is hinged to the bracket, and the fixed end of the electric push rod 204 is hinged to the two first rib plates 202 through the adjusting hole 2021, each profiling mechanism 2 of the embodiment may further include a first pin 205, a second pin 206, and a third pin 207, both ends of the first pin 205 are respectively connected to both sides of the bracket, both ends of the second pin 206 are respectively connected to the two first rib plates 203 through the adjusting hole 2021, both ends of the third pin 206 respectively penetrate through the two second rib plates 203 to be connected to both sides of the bracket, and specifically, the third pin 207 is fixed to the bracket and the second rib plates 203 through the first bearing 208 and maintains a revolute pair; the telescopic end of the electric push rod 204 is fixed on the first pin shaft 205, the fixed end of the electric push rod 204 is fixed on the second pin shaft 206, the electric push rod 204 can move telescopically under the program control of the self-adaptive control system, and the circuit drive can move telescopically, so that the support is driven to rotate around the third pin shaft 207.

Further, the support comprises a first fixing plate 209, a second fixing plate 210, a vertical plate 211 and two side plates 212, the two side plates 212 are relatively fixed on the vertical plate 211, the first fixing plate 209 and the second fixing plate 210 are vertically fixed on the vertical plate and fixedly connected with the two side plates, the first fixing plate 209, the vertical plate 211 and the side plates 212 are arranged between the first fixing plate 209, the second fixing plate 210, the vertical plate 211 and the side plates 212 are fixed between the second fixing plate 210 and the vertical plate 211, and the vertical plate 211 and the side plates 212 are fixed by welding, the first fixing plate 209 is used for fixing a flower thinning shaft corresponding to the flower thinning mechanism 4, specifically, a second bearing 213 is mounted on the first fixing plate 209, and the second bearing 213 can stably rotate concentrically with the flower thinning shaft; the second fixing plate 210 is used to fix the hydraulic motor corresponding to the thinning mechanism 4.

As shown in fig. 4 to 5 and 7 to 8, each flower thinning mechanism 4 is disposed at the front end of the corresponding profiling mechanism 2, each flower thinning mechanism 4 includes a hydraulic motor 401, a coupling 402, a flower thinning shaft 403 and a plurality of flower thinning adhesive tapes 404, the plurality of flower thinning adhesive tapes 404 are disposed on the flower thinning shaft 403, specifically, a threaded hole 4031 and a through hole 4032 are drilled on the flower thinning shaft 403, the direction of the threaded hole 4031 is perpendicular to the direction of the through hole 4032, each flower thinning adhesive tape 404 passes through the through hole 4032, and each flower thinning adhesive tape 404 is fastened on the flower thinning shaft 403 by matching with the threaded hole 4031 through a screw; the sparse shaft 403 is connected with the hydraulic motor 401 through a coupler 402, specifically, one end of the coupler 402 is connected with the coupler 402, and the other end of the coupler 402 is connected with the hydraulic motor 401; the hydraulic motor 401 and the flower thinning shaft 403 are installed on the corresponding profiling mechanism 2, the hydraulic motor 401 is installed on the second fixing plate 210 of the corresponding profiling mechanism 2, and the flower thinning shaft 403 is installed on the first fixing plate 209 of the corresponding profiling mechanism 2; the bottom of the hydraulic motor 401 is provided with a hydraulic oil port 4011, the hydraulic motor 401 is connected with a hydraulic drive station through the hydraulic oil port 4011, the hydraulic motor 401 drives the flower thinning shaft 403 to rotate, and flower thinning operation is completed; meanwhile, the pattern thinning shafts 403 of the three pattern thinning mechanisms 4 are independently adjusted, and the profiling angles and the rotating speeds of the three pattern thinning mechanisms can be kept in various matching modes, so that the self-adaptive pattern thinning operation is achieved.

As shown in fig. 4 to 8, the label inspection mechanism 3 includes a hydraulic cylinder 301, a stay wire type displacement sensor 302, a sensor support 303 and an L-shaped support 304, a beam 201 of each profiling mechanism 2 is mounted on a vertical portion of the L-shaped support 304 and can move relative to the L-shaped support 304, the hydraulic cylinder 301 is mounted on the base mechanism 1, the hydraulic cylinder 301 is connected with a hydraulic drive station, the sensor support 303 is mounted on the hydraulic cylinder 301, the stay wire type displacement sensor 302 is mounted on the L-shaped support 304, specifically, the stay wire type displacement sensor 302 is fixedly mounted on a sensor fixing frame 305, the sensor fixing frame 305 is fixedly mounted on the L-shaped support 304, the sensor fixing frame 305 can be obtained by 3D printing, the stay wire type displacement sensor 302 is connected with the sensor support 303 through a stay wire, and the stay wire type displacement sensor 302 is connected with an adaptive control system; when hydraulic cylinder 301 stretches and retracts, pull-wire displacement sensor 302 and sensor bracket 303 cooperate to complete signal detection of pull-wire displacement sensor 302, and complete output of a movement distance value of hydraulic cylinder 301.

The mark inspection mechanism 3, the three profiling mechanisms 2 and the three flower thinning mechanisms 4 of the embodiment form a single-sided three-section type self-adaptive flower thinning device, and the number of sections or the number of edges can be increased or decreased in the later period.

As shown in fig. 4 to 9, the base mechanism 1 includes a base support 101, a mounting frame 102, a first support member, a second support member, a first support column 103, a second support column 104 and a third support column 105, wherein the first support column 103, the second support column 104 and the third support column 105 are fixed on the base support 101 sequentially from front to back, and specifically, the first support column 103, the second support column 104 and the third support column 105 are fixed on the base support 101 by welding; the first supporting part is arranged on the first support column 103, the second supporting part is arranged on the second support column 104, and the first supporting part and the second supporting part are used for supporting the mark patrol mechanism 3; the mounting frame 102 is fixed on the third support column 105, the mounting frame 102 is fixed on the third support column 105 through a welding mode, and the mounting frame 102 is used for mounting a hydraulic oil cylinder 301 of the patrol mechanism 3.

Further, the first support part comprises two first support shafts 106, the second support part comprises two second support shafts 107, and the first support shafts 106 and the second support shafts 107 are both steel shafts; the number of the first support 103 and the second support 104 is two; two ends of the first support shaft 106 are respectively connected with the two first struts 103, specifically, a first bearing fixing sleeve 108 is installed on each first strut 103, a third bearing is installed in the first bearing fixing sleeve 108, and the third bearing is installed in cooperation with the first support shaft 106; two ends of the second support shaft 106 are respectively connected with the two second struts 103, specifically, a second bearing fixing sleeve 109 is installed on each second strut 104, a fourth bearing is installed in the second bearing fixing sleeve 108, and the fourth bearing is installed in cooperation with the second support shaft 107; the mark inspection mechanism 3 is arranged between the two first supporting shafts 106 and between the two second supporting shafts 107 through clearance fit, and specifically, the transverse part of the L-shaped bracket 304 of the mark inspection mechanism 3 is arranged between the two first supporting shafts 106 and between the two second supporting shafts 107 through clearance fit; the holes are opened, positioned, welded, installed and matched according to the design size.

In the intelligent flower density recognition system of this embodiment, the camera 6 is connected with the processor, the camera is a horizontal visual angle, and the processor is connected with the adaptive control system.

The camera 6 is a color camera, is perpendicular to the ground, has a horizontal visual angle, has a visual field including the whole thinning working range, can collect complete image information, and is mainly used for shooting images of fruit trees and flowers.

Further, the intelligent flower density recognition system of this embodiment still includes adjustable support rod 10, can adjust the height of camera 6 through adjustable support rod 10, guarantees to shoot the field of vision.

Further, in order to keep the stability of camera 6, the intelligent visual identification system of fruit tree flower volume of this embodiment still includes the stabilizer, and camera 6 is fixed on the upper portion of stabilizer, and the lower part of stabilizer links to each other with adjustable support rod 10, can adjust the height that support rod 10 is through adjusting the stabilizer, and then adjusts the height of camera 6, and the stabilizer can slow down the shake and the vibrations influence of self-adaptation flower thinning machine motion.

Further, in order to alleviate the vibrations, the noise influence of self-adaptation flower thinning machine to the treater, the intelligent visual identification system of fruit tree flower volume of this embodiment still includes the bradyseism platform, and the bradyseism platform is installed on crawler chassis 5, and adjustable support rod 10 is installed on the bradyseism platform, and the treater setting is in the bradyseism platform, and the bradyseism platform can guarantee that the treater normally works.

Further, the processor may implement the following process:

acquiring a plurality of fruit tree flower images; denoising and standardizing each fruit tree flower image; extracting a fruit tree flower and leaf feature map in the processed fruit tree flower and leaf image by using a trained deep convolutional neural network; generating a fruit tree flower and leaf prediction map according to the fruit tree flower and leaf characteristic map so as to obtain a fruit tree flower and leaf segmentation map; counting the number of pixels belonging to flowers and the number of pixels belonging to leaves according to the fruit tree flower and leaf segmentation map; calculating the density of the flower according to the number of the pixels of the flower and the number of the pixels of the leaves; the density of flowers in each image of the fruit tree flower is converted to an analog quantity.

The denoising and standardization processing of each fruit tree flower image specifically comprises the following steps: denoising the fruit tree flower image by using median filtering; calculating the mean value and standard deviation of RGB three channel components of the denoised consequence tree flower image; according to the mean value and the standard deviation, the denoised consequence tree flower image is subjected to standardized calculation, the value range of the calculated image is 0 to 1, and the influence caused by transformation in the feature extraction process can be effectively reduced; and extracting the characteristic map of the flower and leaf of the fruit tree in the processed image of the flower and the fruit tree by using the trained deep convolutional neural network.

The deep convolutional neural network is shown in fig. 10 and comprises a trunk network and a pyramid structure, wherein the trunk network comprises two parts, namely a transition feature extraction part (part 1 in the figure) and a trunk feature extraction part (part 2 in the figure), and the transition feature extraction part, the trunk feature extraction part and the pyramid structure are sequentially connected.

The transition feature extraction part is a shallow layer network, and comprises a first convolution layer, a second convolution layer and a third convolution layer which are sequentially connected, and is mainly used for learning general features such as textures, angular points and the like, wherein the first convolution layer, the second convolution layer and the third convolution layer are convolution layers of a 3 x 3 convolution kernel in the embodiment.

The main feature extraction part is a deep network, a convolution-activation-normalization convolution block which is continuously stacked in 32 layers in depth is used as a main body and is divided into four stages which are sequentially connected, the four stages are respectively a 1 st stage, a 2 nd stage, a 3 rd stage and a 4 th stage, 6, 8, 12 and 6 convolution blocks are respectively arranged from the 1 st stage to the 4 th stage, every two continuous convolution blocks form a residual error module, specific features related to a main learning task are mainly learned, and each residual error module is linearly fused with the identity mapping of the output features and the input features of the two convolution blocks and then is used as the input of a subsequent convolution block. The output feature quantity of the convolution block in the same stage is the same as that of the initial input of the stage, the feature quantity of the cross-stage is different, the convolution layer using 1 multiplied by 1 convolution kernel adjusts the feature quantity, and each convolution is completed by being processed by an activation function and a normalization layer. In each convolution block, the convolution is to process the feature using a 3 × 3 convolution kernel, then input to the activation function, and finally undergo normalization layer processing.

Further, a hole convolution structure is added into the convolution blocks in the 3 rd stage and the 4 th stage, and the hole convolution means that 0 values of interval rules are inserted into a convolution kernel to enlarge the size of the convolution kernel, so that the receptive field of deep features is expanded, the operation amount is not increased, and meanwhile, the maximum pooling is replaced by adjusting the sliding stride of filtering operation to reduce the loss of feature information; in the embodiment, in order to better extract the characteristics of the fruit tree flowers, a convolution structure with a small cavity rate is more suitable.

Furthermore, an attention module is added between every two adjacent stages, the attention module compresses the features with the size of w × h into 1 × 1, then a learnable linear connection layer is input to obtain weight vectors of the features of different channels, each weight measures the importance degree of the input features, and the weights are broadcasted into the size of the input features and then multiplied by the original input features to play a role in screening the features.

In order to increase the richness of the learning features of the convolutional layers, dense feature connection is selectively realized according to the action of the deep and shallow convolutional layers, specifically dense feature connection is realized on deep features, the connection mode is shown as fig. 4, dense feature connection means that the input features of the next layer are the output features of all previous layers, as described above, the shallow network learning textures, corners and other general features, the deep network learning tasks have specific features, and the features of the over-shallow layer and the over-deep layer have larger difference, so that the dense connection range is adjusted to ensure the richness and consistency of feature extraction.

After the trunk features are extracted, the trunk features are processed by using a pyramid structure, and the learning capability of the network multi-scale features is enhanced; in the pyramid structure, four convolutional layers with different voidages and filter steps are used for processing input intermediate features in parallel, then the input features and the features processed in parallel are spliced in feature dimensions, finally fusion and correction are carried out through 3 x 3 convolutional layers to obtain a multi-scale fruit flower and leaf feature map, 1280 fruit flower and leaf feature maps are obtained, and the size of the fruit flower and leaf feature map is 1/16 of an input image.

The method comprises the following steps of generating a fruit tree flower and leaf prediction graph according to a fruit tree flower and leaf characteristic graph, so as to obtain a fruit tree flower and leaf segmentation graph, wherein the fruit tree flower and leaf prediction graph is realized by constructing a prediction layer, the prediction layer comprises two rolling blocks, the kernel size of the first rolling block is 3 multiplied by 3, the kernel size of the second rolling block is 1 multiplied by 1, and the method specifically comprises the following steps: fusing the characteristic map of the flower and leaf of the fruit tree through a first rolling block to obtain a first characteristic map, wherein the kernel size of the first rolling block is 3 multiplied by 3; inputting the first feature map into a second volume block to obtain a second feature map, wherein the kernel size of the second volume block is 1 multiplied by 1; mapping the second characteristic map into three probability prediction maps respectively representing flowers, leaves and background of the fruit tree through a full convolution layer; solving the maximum value of the three probability prediction graphs on the characteristic dimension to obtain a fruit tree flower and leaf prediction graph; and superposing the fruit tree flower and leaf prediction image and the fruit tree flower and leaf characteristic image according to preset weight to obtain a fruit tree flower and leaf segmentation image.

Wherein, according to the number of pixels of the flower and the number of pixels of the leaves, the density of the flower is calculated, and the method specifically comprises the following steps: summing the number of the pixels of the flowers and the number of the pixels of the leaves to obtain the total number of the pixels; the flower density is obtained by dividing the number of flower pixels by the total number of pixels.

Wherein, the density of flowers in each fruit tree flower image is converted into analog quantity, and the method specifically comprises the following steps: according to the density of flowers in all the fruit tree flower images, calculating the maximum value and the minimum value as the upper limit and the lower limit of the conversion between the density of the flowers and the analog quantity; scaling the density range of the flowers to be between 0 and 1 by using a maximum and minimum normalization method according to the upper limit and the lower limit of the conversion of the density of the flowers and the analog quantity, and enabling the analog quantity range to be between 4 and 20 milliamperes; constructing a mapping relation between a density range and an analog quantity range of the flower by using linear scaling; and converting the flower density in each fruit tree flower image into an analog quantity according to the mapping relation between the flower density range and the analog quantity range.

The hydraulic drive station is a hydraulic system, and the principle of the hydraulic drive station is shown in fig. 11, in the hydraulic drive station of the embodiment, a hydraulic control element 9 is respectively connected with a hydraulic motor 401 of the flower thinning mechanism 4, a hydraulic oil cylinder 301 of the label inspection mechanism 3 and a power source, and the power source 8 is connected with the crawler chassis 5.

Further, power supply 8 includes gasoline engine, shaft coupling and oil pump, and the gasoline engine provides power for hydraulic drive station, can provide power for track chassis 5, and the gasoline engine passes through the shaft coupling with the axle center with the oil pump to be connected, and the oil pump supplies oil for the gasoline engine.

Further, the hydraulic control element 9 includes a proportional valve, a proportional amplifier, a balance valve, a pressure stabilizing valve, a pressure reducing valve, a hydraulic valve block and a one-way valve, the balance valve, the pressure stabilizing valve, the pressure reducing valve and the hydraulic valve block constitute a basic hydraulic control part, and an intelligent regulation hydraulic control loop is formed by combining the balance valve and the proportional amplifier, and the proportional valve is connected with the hydraulic motor 401 and the hydraulic oil cylinder 301.

Further, the hydraulic drive station of the present embodiment may further include auxiliary components, where the auxiliary components include a hydraulic oil tank and a hydraulic oil pipe, the hydraulic oil tank supplies oil to the hydraulic control component 9, and the oil pipe provides a circuit for the hydraulic control component 9.

The principle of the adaptive control system is shown in fig. 12, and the adaptive control system of this embodiment includes an upper computer, a Programmable Logic Controller (PLC), an analog-to-digital conversion module, a digital-to-analog conversion module, a communication module, and a relay group, where the Programmable Logic Controller is connected to the electric push rod 204 of the profiling mechanism 2, the pull-wire displacement sensor 302 of the sighting mark mechanism 3, the analog-to-digital conversion module, the digital-to-analog conversion module, the communication module, and the relay group, and the communication module is connected to the upper computer, and the Programmable Logic Controller is a control core of the adaptive control system and can transmit information to the upper computer, and the upper computer can also control the Programmable Logic Controller by entering an instruction, and the analog-to-digital conversion module is connected to a processor of the intelligent flower density recognition system, and is connected to a proportional amplifier of the hydraulic drive station, and the relay group is connected to the proportional amplifier of the hydraulic drive station, The proportional valve is connected, the relay can control the on-off copying of the proportional valve, and the proportional amplifier is matched with the relay to control the direction and the flow value of the proportional valve; the upper computer can be an industrial control touch screen or a remote controller, when the upper computer is the industrial control touch screen, the communication module is a serial communication module, when the upper computer is the remote controller, the communication module is a wireless receiver, and the upper computer can refresh and display in real time to realize the series of functions of human-computer interaction.

In this embodiment, intelligence flower density identification system can discern fruit tree flower density in real time and convert information into serial communication standard quantity (digital quantity) through analog-to-digital conversion module, transmit in the programmable logic controller, the programmable logic controller can be through program processing with the signal that transmits, give the instruction to digital-to-analog conversion module, digital-to-analog conversion module can convert the instruction that the programmable logic controller was given into standard analog quantity control proportional amplifier, proportional amplifier can amplify the current value of the signal of telecommunication according to standard equal proportion, drive proportional valve action, control hydraulic motor and hydraulic cylinder speed, programmable logic controller passes through delivery outlet Y simultaneously, give the relay signal, control electric putter and proportional amplifier work.

The adaptivity of the embodiment is shown in the following steps: the intelligent flower density recognition system can convert the collected fruit tree flower position and fruit tree flower density information into analog quantity, and the analog quantity is transferred to the programmable logic controller through the communication module, and the programmable logic controller can compare the pre-written self-adaptive model and algorithm through a program according to the information, and issue a specific instruction, so that the control of the profiling mechanism, the mark inspection mechanism and the flower thinning mechanism is completed, the goal of inspecting the mark speed and position is reached, the positive and negative moving distance of an electric push rod of the profiling mechanism is reached, the positive and negative rotating speed of a flower thinning shaft of the flower thinning mechanism is controlled, and the self-adaptive control is completed.

The multi-section self-adaptive flower thinning device is not only suitable for flower thinning work, but also suitable for orchard fruit thinning and picking work by adjusting and exploring the spacing of flower thinning adhesive tapes, the material of the flower thinning adhesive tapes, the rotating speed of a flower thinning shaft, the walking speed of an operation carrier and other factors, and can realize fruit tree patrol marking profiling trimming and green belt shaping.

The embodiment also provides a flower thinning method, which is mainly realized by the self-adaptive flower thinning machine, and comprises the following steps:

s1, before thinning flowers of fruit trees in the same row, pre-adjusting the extending distance of the cross beam of the profiling mechanism according to the age of the fruit trees and the tree shapes of the fruit trees, and ensuring the operation range of the patrol mechanism and the profiling work of the canopy of the fruit trees.

And S2, after the intelligent flower density recognition system reaches the position to be thinned, intelligently recognizing the flower density recognition system to obtain the position and density information of the fruit tree flowers, and transmitting the information to the self-adaptive control system.

And S3, after receiving the information transmitted by the intelligent flower density recognition system, the self-adaptive control system judges the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft, and converts the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft into a control quantity of the hydraulic drive station and a control quantity of an electric push rod of the profiling mechanism.

And S4, after the relative position of the fruit tree to be thinned is reached, the patrol mark mechanism moves after the adaptive control system sends an instruction, so that the thinning mechanism moves horizontally to finish patrol mark work, and the distance between the patrol mark mechanism and the fruit tree to be thinned is ensured to be within a constant range.

S5, according to the branch position to be thinned of the fruit tree to be thinned, a plurality of profiling mechanisms work simultaneously, the action of an electric push rod of the profiling mechanism is controlled, and precise profiling is guaranteed.

S6, after copying, controlling the hydraulic motor of the flower thinning mechanism to act to drive the flower thinning shaft and the flower thinning adhesive tape of the flower thinning mechanism to rotate, and carrying out self-adaptive flower thinning operation on branches to be thinned of the fruit tree to be thinned, wherein the self-adaptive flower thinning operation comprises the steps of overall mark patrol, single-pitch arm (each copying mechanism and the corresponding flower thinning mechanism) copying, and different or equal speed values.

In the description of the present invention, it should be noted that, unless otherwise explicitly specified or given otherwise, the terms "disposed," "mounted," and "connected" are to be construed broadly, e.g., the connection may be a fixed connection, a detachable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In conclusion, the intelligent flower density recognition system is used for intelligently recognizing the position of the fruit tree flower and the flower density information of the fruit tree flower, the information is transmitted to the self-adaptive control system, the self-adaptive control system judges the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft after receiving the information transmitted by the intelligent flower density recognition system, and the patrol mark displacement, the profiling angle and the rotation speed of the flower thinning shaft are converted into the control quantity of the hydraulic drive station and the control quantity of the electric push rod of the profiling mechanism, so that the self-adaptive flower thinning operation is completed, the fruit tree flower recognition precision and the self-adaptive flower thinning capability can be improved, the labor intensity is reduced, and the flower thinning efficiency and the flower thinning proportion are improved.

The above description is only for the preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and the inventive concept of the present invention within the scope of the present invention.

Claims (8)

1. A self-adaptive flower thinning machine is characterized by comprising an operation carrier, a multi-section self-adaptive flower thinning device, an intelligent flower density recognition system, a self-adaptive control system and a hydraulic drive station, wherein the multi-section self-adaptive flower thinning device, the intelligent flower density recognition system, the self-adaptive control system and the hydraulic drive station are arranged on the operation carrier;

the multi-section self-adaptive flower thinning device comprises a base mechanism, a plurality of profiling mechanisms, a label patrolling mechanism and a flower thinning mechanism, wherein the label patrolling mechanism is arranged on the base mechanism, the profiling mechanisms and the flower thinning mechanism are multiple, the profiling mechanisms and the flower thinning mechanisms are in one-to-one correspondence, each flower thinning mechanism is arranged on the corresponding profiling mechanism, the profiling mechanisms are sequentially arranged on the label patrolling mechanism from top to bottom, the profiling mechanisms can move relative to the label patrolling mechanism, and the label patrolling mechanism can move relative to the base mechanism to complete target searching and positioning;

the self-adaptive control system is respectively connected with the profiling mechanism, the label patrol mechanism, the hydraulic drive station and the intelligent flower density recognition system, and the hydraulic drive station is respectively connected with the flower thinning mechanism, the label patrol mechanism and the operation carrier;

each profiling mechanism comprises a cross beam, two first rib plates, two second rib plates, an electric push rod and a support, the cross beam is installed on the label walking mechanism, the number of the first rib plates and the number of the second rib plates are two, the two first rib plates are fixed between the two ends of the cross beam and are oppositely arranged on the two sides of the cross beam, a plurality of adjusting holes are formed in each first rib plate, the two second rib plates are hinged to the support, the two second rib plates are fixed at the front end of the cross beam and are oppositely arranged on the two sides of the cross beam, the electric push rod is connected with the self-adaptive control system, the telescopic end of the electric push rod is hinged to the support, the fixed end of the electric push rod is hinged to the two first rib plates through the adjusting holes, the electric push rod can drive the support to rotate around the hinged point of the second rib plates and the support, and the support is used for installing a corresponding flower thinning mechanism;

the support comprises a first fixing plate, a second fixing plate, a vertical plate and two side plates, wherein the two side plates are fixed on the vertical plate oppositely, the first fixing plate and the second fixing plate are fixed on the vertical plate up and down and are fixedly connected with the two side plates, the first fixing plate is used for fixing a flower thinning shaft of a corresponding flower thinning mechanism, and the second fixing plate is used for fixing a hydraulic motor of the corresponding flower thinning mechanism; the first fixing plate, the vertical plate and the side plate, the second fixing plate, the vertical plate and the side plate and the vertical plate and the side plate are fixed in a welding mode;

each profiling mechanism further comprises a first pin shaft, a second pin shaft and a third pin shaft, wherein two ends of the first pin shaft are respectively connected with two sides of the support, two ends of the second pin shaft are respectively connected with the two first rib plates through adjusting holes, two ends of the third pin shaft respectively penetrate through the two second rib plates to be connected with two sides of the support, and the third pin shaft is fixed with the support and the second rib plates through a first bearing and keeps a revolute pair; the telescopic end of the electric push rod is fixed on the first pin shaft, the fixed end of the electric push rod is fixed on the second pin shaft, the electric push rod is controlled by a program, and the circuit is driven to telescopically move so as to drive the support to rotate around the third pin shaft.

2. The adaptive flower thinning machine according to claim 1, wherein the intelligent flower density recognition system comprises a camera and a processor, the camera is connected with the processor, the camera has a horizontal viewing angle, the field of view of the camera comprises the whole flower thinning working range, and the processor is connected with the adaptive control system;

the camera is used for shooting the fruit tree flower image;

the processor is used for acquiring a plurality of fruit tree flower images; denoising and standardizing each fruit tree flower image; extracting a fruit tree flower and leaf feature map in the processed fruit tree flower and leaf image by using a trained deep convolutional neural network; generating a fruit tree flower and leaf prediction map according to the fruit tree flower and leaf characteristic map so as to obtain a fruit tree flower and leaf segmentation map; counting the number of pixels belonging to flowers and the number of pixels belonging to leaves according to the fruit tree flower and leaf segmentation map; calculating the density of the flowers according to the number of the pixels of the flowers and the number of the pixels of the leaves; the density of flowers in each image of the fruit tree flower is converted to an analog quantity.

3. The adaptive flower thinning machine according to claim 1, wherein the adaptive control system comprises an upper computer, a programmable logic controller, an analog-to-digital conversion module, a digital-to-analog conversion module, a communication module and a relay set, the programmable logic controller is respectively connected with the profiling mechanism, the label tracking mechanism, the analog-to-digital conversion module, the digital-to-analog conversion module, the communication module and the relay set, the communication module is connected with the upper computer, the analog-to-digital conversion module is connected with the intelligent flower density recognition system, and the digital-to-analog conversion module and the relay set are connected with the hydraulic drive station.

4. The adaptive flower thinning machine according to claim 1, wherein the hydraulic driving station comprises a power source and a hydraulic control element, the hydraulic control element is respectively connected with the flower thinning mechanism, the label tracking mechanism and the power source, and the power source is connected with the operation carrier.

5. The adaptive flower thinning machine according to any one of claims 1 to 4, wherein each flower thinning mechanism comprises a plurality of hydraulic motors, couplers, flower thinning shafts and flower thinning rubber strips, the plurality of flower thinning rubber strips are arranged on the flower thinning shafts, the flower thinning shafts are connected with the hydraulic motors through the couplers, the hydraulic motors and the flower thinning shafts are mounted on the corresponding profiling mechanisms, and the hydraulic motors are connected with the hydraulic driving stations.

6. The adaptive flower thinning machine according to any one of claims 1-4, wherein the label patrol mechanism comprises a hydraulic cylinder, a stay wire type displacement sensor, a sensor bracket and an L-shaped bracket, the hydraulic cylinder is arranged on the base mechanism, the hydraulic cylinder is connected with the hydraulic drive station, the sensor bracket is arranged on the hydraulic cylinder, the stay wire type displacement sensor is arranged on the L-shaped bracket, the stay wire type displacement sensor is connected with the sensor bracket through a stay wire, the stay wire type displacement sensor is connected with the adaptive control system, and the beam is arranged on the vertical part of the L-shaped bracket.

7. The adaptive flower thinning machine according to any one of claims 1 to 4, wherein the base mechanism comprises a base support, a mounting frame, a first support part, a second support part, a first pillar, a second pillar and a third pillar, the first pillar, the second pillar and the third pillar are sequentially fixed on the base support from front to back, the first support part is arranged on the first pillar, the second support part is arranged on the second pillar, the first support part and the second support part are used for supporting the marking mechanism, the mounting frame is fixed on the third pillar, and the mounting frame is used for mounting a hydraulic oil cylinder of the marking mechanism.

8. A flower thinning method implemented on the adaptive flower thinning machine according to any one of claims 1 to 7, the method comprising:

the method comprises the following steps that before the same row of fruit trees is thinned, the extending distance of a cross beam of a profiling mechanism is pre-adjusted according to the age and the shape of the fruit trees, so that the operation range of a mark inspection mechanism and the profiling work of the canopy of the fruit trees are ensured;

after the intelligent flower density recognition system reaches the position to be thinned, the intelligent flower density recognition system carries out intelligent recognition to obtain information of the position and the density of the fruit tree flowers, and the information is transmitted to the self-adaptive control system;

after receiving the information transmitted by the intelligent flower density recognition system, the self-adaptive control system judges the patrol displacement, the profiling angle and the rotational speed of the flower thinning shaft, and converts the patrol displacement, the profiling angle and the rotational speed of the flower thinning shaft into a control quantity of a hydraulic drive station and a control quantity of an electric push rod of a profiling mechanism;

after the relative position of the fruit tree to be thinned is reached, the patrol mechanism acts after the adaptive control system sends an instruction, so that the thinning mechanism moves horizontally to finish patrol, and the distance between the patrol mechanism and the fruit tree to be thinned is ensured to be within a constant range;

according to the branch part to be thinned of the fruit tree to be thinned, a plurality of profiling mechanisms work simultaneously, and the action of an electric push rod of the profiling mechanism is controlled, so that the precision profiling is ensured;

after profiling, the hydraulic motor of the flower thinning mechanism is controlled to act to drive the flower thinning shaft and the flower thinning adhesive tape of the flower thinning mechanism to rotate, and self-adaptive flower thinning operation is carried out on branches to be thinned of fruit trees to be thinned.

Images